Tachyon
Tachyon MCP is a Java and Kotlin server runtime for the Model Context Protocol (MCP) built on Netty that simplifies exposing tools, resources and agent skills; it handles transport, protocol details, task progress, and provides declarative annotated handlers for building MCP servers.
Tachyon is ai agents software teams evaluate for ai agents. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Used in These Packs
Quick Overview
Best for: AI Agents
What it does
AI Agents software for decision-makers comparing workflow fit and alternatives.
Best fit
AI Agents
Pricing snapshot
Pricing available from Free (Apache-2.0)
Next step
Compare Tachyon with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
Tachyon
Tachyon MCP is a server runtime for the Model Context Protocol (MCP) implemented for Java and Kotlin, built on Netty. It lets developers write handlers (annotated or programmatic) while Tachyon manages transport, protocol handling, lifecycle and runtime concerns. The project includes quickstarts and examples for both Java (Maven/Gradle) and a Kotlin DSL, is released on GitHub, and is licensed under Apache-2.0.
Tachyon MCP is a production Model Context Protocol server runtime for Java and Kotlin. Netty transport, virtual threads, stateless by default, MCP 2025-11-25 and 2026-07-28 conformance.
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
Model Context Protocol runtime
Provides a Java and Kotlin runtime for MCP, conformance-tested against MCP 2025-11-25 and 2026-07-28.
Netty-based transport & lifecycle
Netty owns sockets and connection lifecycle; Tachyon uses Netty for transport and lifecycle management.
Declarative annotated services and DSL
Support for annotated Java services and a Kotlin DSL to declare tools and handlers (examples show @McpTool and @McpParam usage and Kotlin DSL declarations).
Tools, prompts and completions
Built-in concepts for tools, resources, templates, prompts and completions to integrate agent capabilities and tooling.
Task support & progress notifications
TasksExtension provides task support (create_task + task://{id}), with server-side progress notifications and TaskSupport options (e.g., REQUIRED).
Skills extension
SkillsExtension can serve agent skills as skill:// resources from filesystem or classpath registries and supports optional negotiation.
Handlers on virtual threads or suspending Kotlin handlers
Run synchronous Java handlers on virtual threads or suspending Kotlin handlers; handlers do not run on the Netty event loop.
Observability
Documentation mentions observability and OpenTelemetry integration for monitoring.
Pricing
Free under the Apache-2.0 license (project releases available on GitHub).
Open-source
Free (Apache-2.0)- Source code and releases on GitHub
- Documentation and quickstarts
Use Cases
Build MCP servers in Java or Kotlin
Create Model Context Protocol servers using Tachyon's builder API, annotations, or Kotlin DSL and deploy via Netty.
Expose tools and long-running tasks to agents
Register tools (get_forecast, generate_report examples) with task support and stream progress notifications back to clients.
Serve agent skills and static skill resources
Use the SkillsExtension to serve SKILL.md and related files from filesystem or classpath registries as skill:// resources.
Integrate prompts and completions into agent workflows
Use built-in primitives for prompts, completions, templates and elicitation to support agent interactions and tool invocation.
Integrations
Netty
Underlying transport and connection lifecycle management is implemented on Netty.
TasksExtension
Provides create_task and task://{id} support and progress notifications for long-running operations.
SkillsExtension (Filesystem and Classpath registries)
Serve agent skills from filesystem or classpath registries and publish under namespaces.
OpenTelemetry
Observability support mentions integration with OpenTelemetry.
Benefits
Limitations
Frequently Asked Questions
No verified FAQs are available.
Getting Started
- 1 Choose Java (Maven/Gradle) or Kotlin DSL quickstart (see documentation).
- 2 Follow the quickstart to declare tools or annotated services (examples use TachyonServer.builder() or Kotlin DSL).
- 3 Build and run the server (examples show server.start() on port 8080) and test tool endpoints.
Support
docs
Documentation and guides available on the Tachyon site (Read the docs / Docs sections).
github
Project releases and source code available on GitHub (Releases on GitHub).
discord
Community/real-time discussion via Discord (page lists GitHub and Discord links).
API
Documentation and API usage examples are available on the Tachyon site (quickstarts and code samples like TachyonServer.builder()).
Compare Tachyon with similar tools
See how it stacks up against alternatives
Related Tools
View all 549 →
Needle2
Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.
The cheapest GPU cloud
Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.
Oodle.ai
Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.
AgentDrive
AgentDrive is a cloud filesystem by Token Canopy that provides durable, shared drives for AI agents and human teammates to store and share files and context across work sessions, with an API intended for direct agent use.
Nous
Nous is an open-source context graph for agentic GTM (go-to-market) teams that centralizes identity-resolved people and company data from multiple GTM tools so agents can read a single, source-traced account context in one call. It is available as a hosted service and as a self-hostable stack.
Premium Alternatives
AletheionAGI
AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.
ClaudeThings
ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code — delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.
Miro
Miro is a collaborative visual workspace and AI platform that integrates intelligent agents (Sidekicks), visual multi-step workflows (Flows), and connectors to bring team context and external data into a shared canvas to accelerate planning, design, and decision-making across organizations.
qomplement
qomplement is an Agentic AI-driven ERP built for supply chain and operations teams that automates tasks across procurement, inventory, freight, finance, and planning to reduce manual work and scale operations without adding headcount.